Hands-On Computer Vision: SLAM, 3d geometry, Calib, AR, Pose

This hands-on course introduces students to 3D computer vision using monocular and stereo cameras. Through a series of real-world projects and coding exercises, learners will build a strong foundation in camera geometry, feature-based matching, pose estimation, and 3D reconstruction targeted for research and industrial application in Autonomous vehicle, robotics, machine learning, 3d geometry and reconstruction. You will begin by understanding camera calibration and how a single camera can be used for localization and height estimation.

You'll then move on to more advanced topics like real-time 3D pose estimation, augmented reality overlays, video stabilization, and visual odometry on real datasets like KITTI. This course is project-driven and emphasizes classical, interpretable methods giving you the tools to develop your own computer vision pipeline without requiring deep learning. What You Will Learn: Camera Calibration & Projection GeometryEstimate intrinsic and extrinsic parameters of monocular camerasUse projection grids for object height estimation Object Localization & 3D Pose EstimationDetect and track objects using feature matchingEstimate 3D object pose and overlay augmented content in real-time Video Stabilization & Image StitchingImplement 2D video stabilization using feature tracking and homographiesPerform planar image stitching using BRISK and homography transformation Feature Detection and MatchingUse BRISK, ORB, and other descriptors for robust keypoint matchingUnderstand outlier rejection using RANSAC Epipolar Geometry & Visual OdometryCompute and visualize the fundamental matrix and epipolar linesApply monocular visual odometry using optical flow and epipolar constraints 3D Triangulation from Stereo ViewsReconstruct 3D point clouds from stereo image pairsUnderstand triangulation using projection matricesSkills You Will Gain:Practical understanding of camera models and calibrationHands-on experience with OpenCV for vision pipelinesReal-time 3D pose estimation and augmented reality overlayProficiency in homography estimation and image registrationBuilding basic visual odometry systems from scratchCreating and visualizing 3D reconstructions using triangulationWorking with real datasets like KITTI for visual SLAM foundationsIdeal For:Engineering and CS studentsRobotics and AR/VR enthusiastsDevelopers interested in classical computer vision techniquesAnyone seeking a practical foundation before diving into deep learning.